CUSTOMER STORYHow this activewear leader personalized digital discovery to elevate online shopping.

A top activewear brand bridged the gap between exceptional in-store service and digital experience, resulting in a 28% increase in conversions.

The in-store experience gap

Customer experience is at the heart of one of the world’s most popular activewear brands. In its stores, the brand provides shoppers (whom it calls “guests”) with premium service via store “educators” (sales associates). Guests are given as much or as little service as they desire. Each store is custom-designed by its educators, localizing the look and feel to the geographic region for a more personalized shopping experience. Classes are offered to support customer interests. Guests are made to feel unique, honored, and valued.

The brand envisioned translating this first-class in-store experience to its website. Inspired by other retailers with exceptional online shopping experiences, it identified several e-commerce features required to achieve this goal, with search, browse, and navigation being critical components.

The limitations of manual curation

At the time, the brand’s search engine was built on Endeca, which powered the homepage, search, browse, and product detail pages. The system required extensive manual intervention—each browse page had to be individually sequenced by a team member, meaning every product type required someone to specify which particular product should appear first, second, third, and so on.

If the search experience still wasn’t sufficient, rules had to be applied to make the engine perform as desired. Manually-created rules were used to facilitate synonyms, create redirects, and more. For the roughly 1,500 products offered, more than 3,000 search rules were used to curate a satisfactory experience. That’s at least two rules for each and every product.

The amount of human intervention required required was not scalable. Nor was it possible for the brand to provide the distinctive experience their online guests deserved while Endeca was under the hood.

Unique products, unique challenges

The brand wasn’t making things easy on the search engine either. Rather than being descriptive, product names were catchy. Names like “Hip Hippie Shorts,” “Set To Jet Pants,” and “Set To Sweat Pants” didn’t give the search engine much insight into actual product features like fabric, fit, and intended activity.

Product descriptions, just as colorful as the names, provided little help, leaving the search engine short on data to index and keeping the demands of the search team high.

Defining a new search strategy

The activewear brand knew it needed a new search tool enhanced by automation, machine learning, and a flexible UI to support a seamless user experience. The team wanted to use its homegrown ML algorithms to customize the search and browse experience in automated, powerful, and sustainable ways.

While the search team could build a custom-designed engine from scratch, capabilities that came off the shelf with pre-built search platforms would take years to replicate. After researching the dizzying number of options in the market, Lucidworks rose to the top.

Beyond platform features, the brand also wanted a partnership that supported its move to delight guests online—someone it could rely on for best practices and implementation help. Lucidworks’ extensive knowledge of crafting search experiences across multiple channels for many of the world’s top retailers aligned perfectly with the brand’s needs.

Finding the right solution

Several features made Lucidworks especially advantageous for the brand:

• Powerful machine learning capabilities that come out of the box
• The ease with which custom-built algorithms can be integrated into the system
• A Predictive Merchandiser that empowers the brand’s merchandisers through an intuitive visual interface

With Black Friday looming, the brand set an ambitious goal of launching the new search experience within four months. The implementation included significant improvements to data feeds:

• Enabling incremental updates to the catalog data instead of just full baseline indexes
• Including not only e-commerce products but also in-store-only items to support omnichannel shopping
• Adding inventory quantities, a feature not used with the previous search engine
• Implementing more comprehensive signal processing for customer behavior

Launch and immediate results

In August, the new Lucidworks-powered search began rolling out. To allow for testing, traffic was gradually increased from 5% to 100%. Browse, menus, and recommendations were also turned over to Lucidworks’ care. The more traffic thrown at the system, the better performance got—enabling better analytics and allowing the brand to more finely tune the experience.

Even when traffic reached 4x the website’s peak traffic of two years earlier, Lucidworks far outperformed the previous system, reducing query response times by 50%. Behind the scenes, the continuous updates reduced batches from fourteen per week down to just one.

Benefits beyond the customer experience

The new system delivered substantial benefits to the brand’s employees as well. Those 3,000 rules the search team had to manage with Endeca were reduced by 97% to a more manageable 100 with Lucidworks. Staff could turn to more engaging and impactful work instead of monotonously adding one thesaurus entry after another.

Another significant advantage was the ability to experiment using A/B testing. This allowed the brand to challenge standard assumptions and either confirm or refute theories using actual data:

• Should women’s clothing always appear above men’s?
• Should discounted products be shown above full-priced items for cost-sensitive guests?

None of this experimentation had been possible with the previous system.

The personalized digital experience

As the brand became more sophisticated with its Lucidworks implementation, it began to provide guests with personalized online experiences tailored to their interests. Customer behavior signals automatically curate the website to the individual, echoing the personalized interactions an educator would provide in-store: suggesting products based on activity, color, or gender preferences.

Lucidworks also provided a window where the brand could observe the language its customers used to search for products. By analyzing search term data, it could more easily speak the language of its guests when describing products, making shoppers feel at home on the website.

Black Friday: The ultimate test

When Black Friday arrived and searches on the brand’s website ramped up to 2,000 queries per second, Lucidworks kept responses rapid, helping process 27,500 orders per hour. Click-to-cart rates increased 28% over the previous year, proving the new search system understood the brand’s guests and knowledgeably guided them to the right products, just like an in-store educator.

The brand had successfully transformed its online shopping experience from a generic, rules-heavy system to an intelligent, personalized platform that truly reflected its commitment to exceptional customer service. By shifting from manual curation to intelligent, signals-based personalization, the activewear leader finally achieved its goal: bringing the human touch of its in-store experience to the digital realm.

---

By implementing Lucidworks’ intelligent search platform, a leading activewear brand reduced query response times by 50%, decreased manual search rules by 97%, and achieved a 28% increase in click-to-cart conversions—proving that in digital retail, personalized discovery is the key to connecting customers with products they love.